© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10695
    Prev
    Next
    INDEX
    Explanations

    government administration agencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīä¸Ģå®ļ
    -0.10
    ä¸įåħĭ
    -0.10
    äºĮåŃĹ
    -0.09
    ECTOR
    -0.09
    خد
    -0.09
    ấn
    -0.09
    .Mockito
    -0.09
    æĹħ
    -0.09
    è¿¢
    -0.09
    æīĢæīĢ
    -0.08
    POSITIVE LOGITS
    æĭ§
    0.09
    å°±è¿Ļæł·
    0.08
    nf
    0.08
    çĸĶ
    0.08
    è¿ĻæŶåĢĻ
    0.08
    绣é¢Ĩ
    0.08
    æĹłçĸij
    0.08
    åĹĶ
    0.08
    ÂŃs
    0.08
    ä¸ĭå±ŀ
    0.07
    Activations Density 0.061%

    No Known Activations